| { |
| "name": "root", |
| "gauges": { |
| "SnowballTarget.Policy.Entropy.mean": { |
| "value": 0.8897759318351746, |
| "min": 0.8713157176971436, |
| "max": 2.8454055786132812, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Entropy.sum": { |
| "value": 8524.943359375, |
| "min": 8434.3359375, |
| "max": 29108.5, |
| "count": 20 |
| }, |
| "SnowballTarget.Step.mean": { |
| "value": 199984.0, |
| "min": 9952.0, |
| "max": 199984.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Step.sum": { |
| "value": 199984.0, |
| "min": 9952.0, |
| "max": 199984.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 13.004950523376465, |
| "min": 0.2596834599971771, |
| "max": 13.004950523376465, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 2535.96533203125, |
| "min": 50.37859344482422, |
| "max": 2633.51611328125, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.EpisodeLength.mean": { |
| "value": 199.0, |
| "min": 199.0, |
| "max": 199.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.EpisodeLength.sum": { |
| "value": 8756.0, |
| "min": 8756.0, |
| "max": 10945.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.mean": { |
| "value": 0.07036161830982048, |
| "min": 0.06376742300493003, |
| "max": 0.0732360678081807, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.sum": { |
| "value": 0.2814464732392819, |
| "min": 0.25512215956890333, |
| "max": 0.3581280989604363, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.ValueLoss.mean": { |
| "value": 0.2113669197641167, |
| "min": 0.12021178136552302, |
| "max": 0.29203593928147764, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.ValueLoss.sum": { |
| "value": 0.8454676790564668, |
| "min": 0.4808471254620921, |
| "max": 1.4279741510456683, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.LearningRate.mean": { |
| "value": 8.082097306000005e-06, |
| "min": 8.082097306000005e-06, |
| "max": 0.000291882002706, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.LearningRate.sum": { |
| "value": 3.232838922400002e-05, |
| "min": 3.232838922400002e-05, |
| "max": 0.00138516003828, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Epsilon.mean": { |
| "value": 0.10538800000000001, |
| "min": 0.10538800000000001, |
| "max": 0.29458799999999996, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Epsilon.sum": { |
| "value": 0.42155200000000004, |
| "min": 0.42155200000000004, |
| "max": 1.42344, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Beta.mean": { |
| "value": 0.0001444306000000001, |
| "min": 0.0001444306000000001, |
| "max": 0.0048649706, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Beta.sum": { |
| "value": 0.0005777224000000004, |
| "min": 0.0005777224000000004, |
| "max": 0.023089828, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.CumulativeReward.mean": { |
| "value": 25.613636363636363, |
| "min": 3.0, |
| "max": 25.654545454545456, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.CumulativeReward.sum": { |
| "value": 1127.0, |
| "min": 132.0, |
| "max": 1411.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.mean": { |
| "value": 25.613636363636363, |
| "min": 3.0, |
| "max": 25.654545454545456, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.sum": { |
| "value": 1127.0, |
| "min": 132.0, |
| "max": 1411.0, |
| "count": 20 |
| }, |
| "SnowballTarget.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 20 |
| }, |
| "SnowballTarget.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 20 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1726841484", |
| "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", |
| "command_line_arguments": "/home/smitsis/deep_rl/unit5/.venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", |
| "mlagents_version": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.4.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1726841734" |
| }, |
| "total": 250.2565667849999, |
| "count": 1, |
| "self": 0.21922201300003508, |
| "children": { |
| "run_training.setup": { |
| "total": 0.008066152000083093, |
| "count": 1, |
| "self": 0.008066152000083093 |
| }, |
| "TrainerController.start_learning": { |
| "total": 250.0292786199998, |
| "count": 1, |
| "self": 0.3744494049788045, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.1301599309999801, |
| "count": 1, |
| "self": 1.1301599309999801 |
| }, |
| "TrainerController.advance": { |
| "total": 248.46295536502112, |
| "count": 18205, |
| "self": 0.17611362897923755, |
| "children": { |
| "env_step": { |
| "total": 248.28684173604188, |
| "count": 18205, |
| "self": 188.25323735595612, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 59.85038412704216, |
| "count": 18205, |
| "self": 0.8951788200661213, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 58.95520530697604, |
| "count": 18205, |
| "self": 58.95520530697604 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.18322025304360068, |
| "count": 18205, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 249.56910770303648, |
| "count": 18205, |
| "is_parallel": true, |
| "self": 131.69782400902795, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0011327610000080313, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004448749996299739, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0006878860003780574, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.0006878860003780574 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.01907473899973411, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00018034699951385846, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00012826900001527974, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00012826900001527974 |
| }, |
| "communicator.exchange": { |
| "total": 0.01827653400005147, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.01827653400005147 |
| }, |
| "steps_from_proto": { |
| "total": 0.0004895890001535008, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0001193390016851481, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0003702499984683527, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.0003702499984683527 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 117.87128369400853, |
| "count": 18204, |
| "is_parallel": true, |
| "self": 3.6427256270253565, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 2.818034960998375, |
| "count": 18204, |
| "is_parallel": true, |
| "self": 2.818034960998375 |
| }, |
| "communicator.exchange": { |
| "total": 99.12198214500086, |
| "count": 18204, |
| "is_parallel": true, |
| "self": 99.12198214500086 |
| }, |
| "steps_from_proto": { |
| "total": 12.288540960983937, |
| "count": 18204, |
| "is_parallel": true, |
| "self": 2.6787367210404227, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 9.609804239943514, |
| "count": 182040, |
| "is_parallel": true, |
| "self": 9.609804239943514 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.87950002127036e-05, |
| "count": 1, |
| "self": 9.87950002127036e-05, |
| "children": { |
| "thread_root": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "trainer_advance": { |
| "total": 248.1274678871264, |
| "count": 171658, |
| "is_parallel": true, |
| "self": 1.7051720840272537, |
| "children": { |
| "process_trajectory": { |
| "total": 127.57708770110003, |
| "count": 171658, |
| "is_parallel": true, |
| "self": 127.22796111109983, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.3491265900001963, |
| "count": 4, |
| "is_parallel": true, |
| "self": 0.3491265900001963 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 118.8452081019991, |
| "count": 90, |
| "is_parallel": true, |
| "self": 30.11821414400265, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 88.72699395799646, |
| "count": 4587, |
| "is_parallel": true, |
| "self": 88.72699395799646 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "TrainerController._save_models": { |
| "total": 0.061615123999672505, |
| "count": 1, |
| "self": 0.0013261059998512792, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.060289017999821226, |
| "count": 1, |
| "self": 0.060289017999821226 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
